KAN在视觉任务中表现强但易受噪声干扰，新方法提升其稳定性。
Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision
- 用平滑正则化和分割去激活增强KAN对噪声的鲁棒性
- 在图像分类与语义分割中验证了KAN的强拟合能力
- 适合研究高效神经网络架构或抗噪模型的开发者
Kolmogorov-Arnold Networks（KAN）作为一种理论上高效的神经网络架构，因其捕捉复杂模式的潜力受到关注。然而其在计算机视觉领域的应用仍相对有限。本研究首次分析了KAN在视觉任务中的潜力，评估了KAN及其卷积变体在图像分类和语义分割中的性能，重点关注不同数据规模和噪声水平下的表现。结果表明，尽管KAN具有更强的拟合能力，但对噪声极为敏感，限制了其鲁棒性。为解决此问题，我们提出一种平滑正则化方法，并引入分割去激活技术。两者均有效提升了KAN的稳定性和泛化能力，证明其在处理复杂视觉数据任务中的可行性。
原文摘要 · Abstract (English)
Kolmogorov-Arnold Networks(KANs), as a theoretically efficient neural network architecture, have garnered attention for their potential in capturing complex patterns. However, their application in computer vision remains relatively unexplored. This study first analyzes the potential of KAN in computer vision tasks, evaluating the performance of KAN and its convolutional variants in image classification and semantic segmentation. The focus is placed on examining their characteristics across varying data scales and noise levels. Results indicate that while KAN exhibits stronger fitting capabilities, it is highly sensitive to noise, limiting its robustness. To address this challenge, we propose a smoothness regularization method and introduce a Segment Deactivation technique. Both approaches enhance KAN's stability and generalization, demonstrating its potential in handling complex visual data tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。